SOTAVerified

Visual Tracking

Visual Tracking is an essential and actively researched problem in the field of computer vision with various real-world applications such as robotic services, smart surveillance systems, autonomous driving, and human-computer interaction. It refers to the automatic estimation of the trajectory of an arbitrary target object, usually specified by a bounding box in the first frame, as it moves around in subsequent video frames.

Source: Learning Reinforced Attentional Representation for End-to-End Visual Tracking

Papers

Showing 226–250 of 525 papers

TitleStatusHype
Efficient Adversarial Attacks for Visual Object Tracking—0
Unsupervised Deep Representation Learning for Real-Time TrackingCode1
Scale Equivariance Improves Siamese TrackingCode1
Visual Tracking by TridentAlign and Context EmbeddingCode1
Tracking-by-Trackers with a Distilled and Reinforced ModelCode1
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationCode1
Accurate Bounding-box Regression with Distance-IoU Loss for Visual Tracking—0
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network ArchitecturesCode1
Exemplar Loss for Siamese Network in Visual Tracking—0
Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination—0
Deep Convolutional Likelihood Particle Filter for Visual Tracking—0
Variational Inference and Learning of Piecewise-linear Dynamical Systems—0
TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking.—0
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention—0
Correlation-Guided Attention for Corner Detection Based Visual Tracking—0
Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks—0
How to Train Your Energy-Based Model for RegressionCode1
Derivation of a Constant Velocity Motion Model for Visual Tracking—0
Fully Convolutional Online TrackingCode1
Distilling Localization for Self-Supervised Representation Learning—0
Beyond Background-Aware Correlation Filters: Adaptive Context Modeling by Hand-Crafted and Deep RGB Features for Visual Tracking—0
Efficient Scale Estimation Methods using Lightweight Deep Convolutional Neural Networks for Visual Tracking—0
Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking—0
High-Performance Long-Term Tracking with Meta-UpdaterCode1
Progressive Multi-Stage Learning for Discriminative Tracking—0
Show:102550
← PrevPage 10 of 21Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ARTrack-LAUC60.3—Unverified
2UNINEXT-HAUC59.3—Unverified
3JointNLTAUC56.9—Unverified
4OSTrackAUC55.9—Unverified
5TransTAUC50.7—Unverified
6AdaSwitcherAUC42—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard61.3—Unverified
2TAPIR (MOVi-E)Average Jaccard59.8—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard57.2—Unverified
2TAPIR (MOVi-E)Average Jaccard57.1—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard84.7—Unverified
2TAPIR (MOVi-E)Average Jaccard84.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (MOVi-E)Average Jaccard66.2—Unverified
2TAPIR (Panning MOVi-E)Average Jaccard62.7—Unverified
#ModelMetricClaimedVerifiedStatus
1TATrack-LAUC71.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SiamFC-lu (Ours)AUC0.32—Unverified
#ModelMetricClaimedVerifiedStatus
1SiamFC-lu (Ours)AUC0.66—Unverified
#ModelMetricClaimedVerifiedStatus
1MDNetScore0.64—Unverified
#ModelMetricClaimedVerifiedStatus
1TATrack-LACCURACY0.85—Unverified